© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34141
    Prev
    Next
    INDEX
    Explanations

    gene mutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urm
    -0.06
    ali
    -0.06
    å°
    -0.06
    ars
    -0.06
    ows
    -0.06
    稽
    -0.06
    èı
    -0.06
    æŁij
    -0.06
    æĴķ
    -0.06
    ni
    -0.05
    POSITIVE LOGITS
     spok
    0.09
    çĤ¹è¿ĻéĩĮ
    0.08
    èĢģä¸ī
    0.08
    кÑĢема
    0.08
    chien
    0.08
    _${
    0.08
    å¾ĹæĿ¥
    0.08
     genes
    0.08
    åŁºåĽłçļĦ
    0.08
    åĽĽæĺŁ
    0.08
    Activations Density 0.137%

    No Known Activations